Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PramodDutta/qaskillsnpx agentmods add skills/pramoddutta/qaskills/first-time-user-testerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pramoddutta/qaskills/first-time-user-tester)<a href="https://agentmods.dev/skills/pramoddutta/qaskills/first-time-user-tester"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/first-time-user-tester/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pramoddutta/qaskills/first-time-user-tester"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/first-time-user-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00029 | $0.09083 |
| Opus 5.5 | $0.00012 | $0.03633 |
| Sonnet 5.5 | $0.00006 | $0.01817 |
| Haiku 4.5 | $0.00003 | $0.00908 |
Grade A, and why
First-Time User Tester scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 1,143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
First-Time User Tester Skill
You are an expert QA automation engineer specializing in testing the first-time user experience (FTUE), onboarding flows, empty states, and progressive disclosure patterns. When the user asks you to write, review, or debug first-time user experience tests, follow these detailed instructions.
Core Principles
- First impressions are permanent -- The first-time user experience determines whether a user becomes a long-term customer or churns immediately. Every onboarding step, empty state, and tutorial must be tested as thoroughly as the core product features.
- Clean state is the starting point -- First-time user tests must begin with absolutely no prior state: no cookies, no localStorage, no IndexedDB data, no cached responses, no session tokens. Any leaked state from previous sessions will give a false impression of the FTUE.
- Empty states are features, not afterthoughts -- When a user has no data, the empty state is the entire experience. Test that empty states provide clear guidance, appropriate calls to action, and accurate descriptions of what the user can expect when they add data.
- Progressive disclosure reduces overwhelm -- Features should be revealed gradually as the user demonstrates readiness. Tests must verify that advanced features are hidden initially and become available at the correct trigger points.
- Every onboarding step must be skippable or completable -- Users must never get stuck in an onboarding flow with no way out. Test that every wizard step can be completed, that skip/dismiss controls work, and that the application is usable after skipping onboarding.
- Permission requests must be contextual -- Requesting notification permissions, location access, or camera access during onboarding without context causes distrust. Tests must verify that permission requests are deferred until the user performs an action that requires them.
- Returning users must not see onboarding again -- Once a user has completed or dismissed onboarding, it should never reappear unless explicitly requested. Tests must verify that onboarding completion state persists across sessions.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 1,143 lines · 29 tokens per session scan A 40681d28ef23
First-Time User Tester is a skill published in the GitHub repository PramodDutta/qaskills (240 stars, last pushed 3d ago), licensed MIT. It adds 29 tokens to every session and 9,083 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
test-case-to-katalon-studio
Convert Katalon True Platform/TestOps manual test cases into Katalon Studio automation inside a local Studio Test Project checkout. Use when you need to author or extend a .tc test case file and its paired Groovy script under Scripts/, keep test case variable GUIDs consistent with the .ts test suite bindings that read…
true-platform-testing
End-to-end Katalon True Platform testing workflow and lifecycle router. Use when one request spans several stages and no single skill owns it, for example analyze a requirement, design and import the cases, build a suite, run it with AI, and report the outcome. Also use to route any testing request across the 7-stage…
playwright-execute
Run Playwright tests or suites and upload the resulting report to Katalon True Platform. Use when you need to execute Playwright scripts, package scripts, spec files, projects, or suites, configure or verify @katalon/playwright-reporter, upload Playwright reports with Katalon CLI/reporter commands, and verify uploaded…
test-case-to-playwright
Convert Katalon True Platform/TestOps manual test cases, test suites, or requirement-linked cases into Playwright TypeScript automation. Use when you need to fetch/read Katalon Platform test cases and implement Playwright scripts, create or adapt a Playwright framework, apply Page Object Model and fixtures, or…
test-maintenance
Maintain and evolve a Katalon True Platform/TestOps regression suite as the application changes. Use when you need to detect which tests broke or became flaky from stability and result history, diagnose whether a case needs repair vs regeneration, repair test assets (update, move, reorganize cases), refresh coverage…
release-qa
Test an AI-built web app like a senior QA engineer before release. Use when the user asks to test, QA, verify, ship, check regressions, inspect a browser flow, or decide whether a web app is ready to launch.